Publications

Operationalising Life Cycle Assessment: Surrogate Models for Real-Time Decision-Making in Production

Kay Langhammer, Michael Ritthoff, George Margetis, Michail Vardakis

September 2026

Brightcon 2026, Aalborg, DK

Abstract

Life-cycle assessments are rarely applied as often to the operational decision-making in production as to the planning stage, despite the significant cumulative environmental impacts of high-volume processes. The bottleneck here is that an LCA is too complex for daily use, and decision-makers in production are not trained to interpret the results.

For the ENCIRCLE project, parameterised LCAs are conducted, using as parameters operational variables. The parameters are varied and used to train a surrogate model with the output, i.e. the life-cycle impacts. To determine the stopping criterion for the calculations, the CO2e footprint from the LCA calculations is compared with the optimisation potential derived from more accurate LCI results.

The approach is being tested in two industrial use cases: galvanising and aluminium recycling. As the surrogate model’s output is integrated into an Reinforcement Learning AI agent as an optimization objective, it must aggregate all impacts into a single normalized value to form its reward function, a requirement present both in the simulation environment where the agent trains, and the live production line in which it will imminently be deployed.
To this end, the values in the damage categories of ReCiPe 2016 are normalised so that a standard use case corresponds to 100%.

An interactive notebook is used to demonstrate how the surrogate model is generated and ported in Brightway 2.5, using the joblib package.

Künstliche Intelligenz für die Kreislaufwirtschaft: Eine systematische Analyse von KI‑Anwendungen zur Unterstützung zirkulärer Strategien

Kay Langhammer, Daniel Wurm, Stephan Ramesohl, Justus von Geibler, Manuel W. Bickel, Holmer Hemsen

June 2026

Abstract

Artificial intelligence (AI) can support the transition to a circular economy (CE) at every stage of the value chain. This means AI can help to conserve resources, extend product lifespans and close material loops as far as possible. However, this can only be achieved if the resource savings are not outweighed by AI’s own resource consumption and if rebound effects are avoided – such as increased consumption resulting from new products or services on the market. This policy paper illustrates potential applications through practical examples and provides recommendations for the socially, economically and environmentally sustainable use of AI in seven key areas of the CE.

Interoperability Requirements for Digital Product Passports in the Circular Economy

Kay Langhammer, Niklas Hoffman, Maximilian Blum

May 2026

SETAC Europe 36ᵗʰ Annual Meeting, Maastricht, NL

Abstract

Access to reliable, interoperable life cycle data is essential for enabling transparent, reproducible and scalable sustainability assessments. As digital product information flows across organisations, sectors and tools, the ability of systems to exchange and interpret data consistently becomes a critical requirement for the emerging Digital Product Passport (DPP). This presentation examines the current landscape of interoperability standards and derives key technical, semantic, syntactic and organisational requirements that can support the development of cross-sectoral, machine-readable and trustworthy sustainability data infrastructures.

Künstliche Intelligenz für die Circular Economy – Ein Werkzeug für die nachhaltige Transformation?

Michael Leitl, Jan Quaing, Birgitt Helms, Kay Langhammer, Johanna Graf, David Rohrschneider, Paul Szabó-Müller

February 2025

Abstract

Artificial intelligence (AI) can support the transition to a circular economy (CE) at every stage of the value chain. This means AI can help to conserve resources, extend product lifespans and close material loops as far as possible. However, this can only be achieved if the resource savings are not outweighed by AI’s own resource consumption and if rebound effects are avoided – such as increased consumption resulting from new products or services on the market. This policy paper illustrates potential applications through practical examples and provides recommendations for the socially, economically and environmentally sustainable use of AI in seven key areas of the CE.